agentleFS
dvy1987dvy1987/agent-loom/.agents/skills/quickstart/SKILL.md

quickstart

Skill4 starsChanged 3 months agoMITView on GitHub

Guided first-run that produces a real verified win in under five minutes using the skill library on a seeded offline fixture. Load when a new user asks how to start, run the demo, try agent-loom, or get a quick win. Also triggers on "quickstart", "first run", "demo agent-loom", "try the skills", or onboarding to the library. Zero external credentials required. Idempotent — safe to run multiple times.

  • Installs packages

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No reference to examples/

    line 112

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Quickstart

You get a new user to a real, verified result in ~5 minutes — not a staged fake. Demo uses safe-change on examples/seed/calc/.

Hard Rules

Zero external credentials — offline fixture only. Invoke a real skill (safe-change) — never simulate success. Idempotent — if fix already applied, run impact map + tests and report "already done." End with one-line "what just happened" + link to examples/ tours. Total flow ≤5 minutes wall clock.


Workflow

Step 1 — Confirm install

User has agent-loom skills visible (.agents/skills/ or global install). If missing, point to README.md Installation.

Step 2 — Run demo (read references/DEMO-FLOW.md)

  1. cd examples/seed/calc (or pass path to verify.sh)
  2. dependency-mapping on divide in calc.py
  3. safe-change — add zero guard; verify fails before fix, passes after
  4. bash .agents/skills/safe-change/scripts/verify.sh examples/seed/calc

Step 3 — Explain

**What just happened:** You ran impact mapping → one verified edit → tests green.
That's the safe-change loop — the library's highest-leverage coding skill.

Step 4 — Next steps

Point to:

  • examples/safe-change-demo/README.md
  • examples/structured-planning-demo/README.md
  • examples/deploy-anywhere-demo/README.md
  • docs/why-agent-loom.md

Gotchas

  • pytest may need pip install pytest once — document if missing.
  • User on Windows: use same paths with forward slashes in agent prompts.

Output Format

## Quickstart complete

Result: [KEPT | already fixed]
Verify: pytest → [pass]
What happened: [one line]
Next: [examples link]

Examples

Full walkthrough: references/DEMO-FLOW.md


Common Rationalizations

ExcuseReality
"Fake a passing test"Destroys trust — run real safe-change.
"Skip install check"User without skills gets a confusing failure.
"Long architecture tour first"Win first, depth second.
"Use a remote repo"Needs network + creds — seed is offline.
"Combine all five skills"One win — safe-change only.

Verification

  • Real skill invoked (not simulated)
  • pytest run on seed fixture
  • User told what happened in one line
  • Next-step links provided

Red Flags

  • Simulated verify pass
  • Demo requires API keys
  • No reference to examples/

Prune Log

Last pruned: 2026-07-05

  • Initial release from high-leverage skill spec (Skill 5 family)

Impact Report

Quickstart: [pass|already-done] | Skill: safe-change | Fixture: examples/seed/calc

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.